backlog
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard command-line tools including
gh(GitHub CLI) for repository interactions andgrepfor local file searching. It employs secure patterns for issue creation by using temporary files (mktemp) and the--body-fileflag to handle multi-line content safely. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes content from external sources.
- Ingestion points: Reads item titles, labels, and bodies from local
BACKLOG.mdfiles and remote GitHub issues viagh issue list. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when reading external content into the agent's context.
- Capability inventory: The agent has the ability to write to the local file system and modify GitHub issues via the
ghtool. - Sanitization: There is no explicit requirement for the agent to sanitize or validate the text retrieved from backlog items before processing it.
Audit Metadata